© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30596
    Prev
    Next
    INDEX
    Explanations

    prone, susceptibility, propensity, tendency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rov
    -0.10
    ç½²
    -0.10
    缮çĿ¹
    -0.09
    é£İåIJ¹
    -0.09
    nea
    -0.09
    çĶŁæ´»è´¨éĩı
    -0.09
    æ¸IJ
    -0.09
     ÑĨена
    -0.09
    éľİ
    -0.09
    åĨ³çŃĸ
    -0.09
    POSITIVE LOGITS
     prone
    0.14
     tendencies
    0.14
    åĢ¾åIJij
    0.13
     tendency
    0.13
    è¿Ļæĸ¹éĿ¢
    0.12
     propensity
    0.12
    天çĶŁ
    0.11
    æľĢ容æĺĵ
    0.11
    æĺĵ
    0.10
    endency
    0.10
    Activations Density 0.189%

    No Known Activations